learning_rate: 1e-05
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 400
training_steps: 3000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
1.4334	0.7630	100	1.0494	72.2732	28.1859
0.9941	1.5188	200	0.8512	63.5631	24.9170
0.7004	2.2747	300	0.7689	60.1091	23.0066
0.6149	3.0305	400	0.7136	56.9791	23.1324
0.48	3.7935	500	0.7019	56.0939	20.9567
0.2873	4.5494	600	0.7126	54.2681	20.2168
0.2662	5.3052	700	0.7403	55.5090	20.8096
0.1792	6.0610	800	0.7632	54.2128	19.5224
0.1018	6.8240	900	0.7796	54.5843	20.1046
0.0706	7.5799	1000	0.8194	52.8138	18.7567
0.057	8.3357	1100	0.8403	54.4815	20.3472
0.0296	9.0916	1200	0.8704	53.5963	19.3738
0.019	9.8546	1300	0.8982	54.4341	19.9060
0.0151	10.6104	1400	0.9124	53.6279	19.5209
0.0084	11.3662	1500	0.9445	53.3750	19.1646
0.0068	12.1221	1600	0.9629	53.2011	19.2404
0.0056	12.8851	1700	0.9643	53.2248	19.2965

khier12/480min_whisper_small_FT

480min_whisper_small_FT